P
AI for Archivist
1
of 5

What you'll accomplish

Manual transcription runs 4–6 hours per hour of audio. This two-step workflow cuts that to 30–60 minutes: a free AI tool generates the rough transcript, then Claude cleans it up to archival quality. The result is a searchable, properly formatted text file ready for your digital repository.

What you'll need

  • The audio recording file (MP3, WAV, or M4A format)
  • A free account at otter.ai (Otter AI), which includes 600 minutes/month, or use the web-based Whisper at openai.com/research/whisper
  • A Claude account at {{tool:Claude.url}}. Free tier works for individual transcripts
  • Time needed: 30–45 minutes setup; then 30–60 minutes per hour of audio ongoing
  • Cost: Otter free tier (600 min/month); Claude free; or Otter Business (~$17/month) for higher volume

How-To Guide: Transcribe Oral History Recordings with AI

Step 1: Prepare your audio file

Before transcribing, ensure your audio file is accessible on your computer. Check that:

  • The recording is clear (background noise significantly reduces accuracy)
  • You have the speaker's name(s) for attribution
  • You know the approximate duration

If your recording is on cassette or other physical media, you'll need to digitize it first using a USB audio interface and free software like Audacity.

Tools:Claude